Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1221 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5376. Min Range: -3.5376
Max Act: 3.5376. Min Act: -0.1700
Data Index: 491543 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5376. Min Range: -3.5376
Max Act: 3.4750. Min Act: -0.1700
Data Index: 1744856 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5376. Min Range: -3.5376
Max Act: 3.4436. Min Act: -0.1700
Data Index: 6477839 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5376. Min Range: -3.5376
Max Act: 3.4123. Min Act: -0.1700
Data Index: 3984848 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5376. Min Range: -3.5376
Max Act: 3.3966. Min Act: -0.1700
Data Index: 762051 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5376. Min Range: -3.5376
Max Act: 3.3495. Min Act: -0.1700
Data Index: 5976860 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5376. Min Range: -3.5376
Max Act: 3.3339. Min Act: -0.1700
Data Index: 5436786 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5376. Min Range: -3.5376
Max Act: 3.3339. Min Act: -0.1700
Data Index: 1560096 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5376. Min Range: -3.5376
Max Act: 3.2868. Min Act: -0.1700
Data Index: 8168466 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5376. Min Range: -3.5376
Max Act: 3.2868. Min Act: -0.1700
Data Index: 1161864 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5376. Min Range: -3.5376
Max Act: 3.2868. Min Act: -0.1700
Data Index: 3973757 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5376. Min Range: -3.5376
Max Act: 3.2868. Min Act: -0.1700
Data Index: 5097200 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5376. Min Range: -3.5376
Max Act: 3.3025. Min Act: -0.1700
Data Index: 782509 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5376. Min Range: -3.5376
Max Act: 3.2711. Min Act: -0.1700
Data Index: 6690587 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5376. Min Range: -3.5376
Max Act: 3.2711. Min Act: -0.1700
Data Index: 5548122 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5376. Min Range: -3.5376
Max Act: 3.2711. Min Act: -0.1700
Data Index: 7441241 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5376. Min Range: -3.5376
Max Act: 3.2711. Min Act: -0.1700
Data Index: 6915725 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5376. Min Range: -3.5376
Max Act: 3.2711. Min Act: -0.1700
Data Index: 4747638 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5376. Min Range: -3.5376
Max Act: 3.2554. Min Act: -0.1700
Data Index: 5471334 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5376. Min Range: -3.5376
Max Act: 3.2554. Min Act: -0.1700
Data Index: 1049736 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19